Skip to main content
Glama

Corey James portfolio

search_portfolio

Search the systems, engineering stories, capabilities, ideas, technologies, patent applications and the agent gallery. Returns ranked pages with their measured results and links; an agent role lists the specialists that matched inside it. Without a kind, pages with measured results lead and at most two agent results are returned.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_portfolio"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
limitNo
queryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "system",
      -  "story",
      -  "capability",
      -  "idea",
      -  "technology",
      -  "patent-family",
      -  "tool-group"
      -]New value: +[
      +  "system",
      +  "story",
      +  "capability",
      +  "idea",
      +  "technology",
      +  "patent-family",
      +  "tool-group",
      +  "agent-role",
      +  "agent-specialist",
      +  "agent-function",
      +  "agent-gallery"
      +]
  2. First observed

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does disclose non-obvious behavior: results are ranked, pages come with measured results and links, agent-role results enumerate matched specialists, and the no-`kind` case caps agent results at two. It stops short of stating pagination behavior, whether the search is read-only/exhaustive, or any limits beyond the agent cap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the verb and corpus, then return shape, then the default-behavior caveat. Dense domain vocabulary ("pages," "measured results") is used without definition, which slightly reduces the payoff per sentence but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With three parameters, one enum of eleven opaque values, and no output schema, the description must explain both the kind vocabulary and the return shape. It gives a credible sketch of returns and the default ranking rule, but leaves the majority of `kind` values and the `query` semantics undefined, so an agent still has to guess for many calls.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It partially does for `kind`, enumerating the indexable categories and describing the default when absent, but `query` (matching semantics, phrase support) and `limit` (beyond the schema's 1-25 bounds) are not addressed at all, and several enum values such as agent-function and tool-group go unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ("Search") plus an enumerated set of resources (systems, stories, capabilities, ideas, technologies, patent applications, agent gallery), which gives an agent a concrete sense of corpus scope. It does not name siblings such as list_systems or list_capabilities to explain why one would search rather than list, so differentiation is implied by the verb rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the description clarifies what happens when `kind` is omitted (measured-result pages lead, at most two agent results), which is a real usage decision, but it never says when to prefer this over the sibling list_* tools or the plain `search` tool. No exclusions or prerequisites are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources